[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M76YRG9BZK5DGVVH3B2DP1G1":3,"skill-same:01M76YRG9BZK5DGVVH3B2DP1G1":193},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":114,"commitSha":115,"skillDirectory":116,"forksCount":117,"repositoryHtmlUrl":118,"repositoryHomepageUrl":6,"ownerHtmlUrl":119,"ownerBlogUrl":120,"ownerDescription":6,"updatedAt":121,"install":122,"resources":135},"01M76YRG9BZK5DGVVH3B2DP1G1","turingdb-graph",null,"Build, query, and analyse biomedical knowledge graphs in TuringDB, a columnar graph database with git-like versioning.","stanfish06\u002Fskillquarium","stanfish06","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F93099613?v=4","01M75F1CK4ZW109ZK3T26VN52F","Zhiyuan","01M75F1CM53VH6F79DZ8GXKKES",12,"MIT","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fturingdb-graph\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: turingdb-graph\ndescription: Build, query, and analyse biomedical knowledge graphs in TuringDB, a columnar graph database with git-like versioning.\nlicense: MIT\nmetadata:\n  version: 0.1.0\n  author: TuringDB \u003Cteam@turingdb.ai>\n  domain: graph-analytics\n  tags:\n  - graph-database\n  - knowledge-graph\n  - turingdb\n  - cypher\n  - biomedical\n  - patient-cohort\n  - pathway\n  inputs:\n  - name: input_file\n    type: file\n    format:\n    - csv\n    - tsv\n    - gml\n    - jsonl\n    description: 'Graph source file for --build. CSV\u002FTSV: one node per row (requires --node-label). GML: nodes become GMLNode.\n      JSONL: typed nodes and edges (Neo4j APOC-compatible).'\n    required: false\n  - name: cypher\n    type: string\n    description: Cypher query string for --query. TuringDB supports a subset of openCypher.\n    required: false\n  - name: graph\n    type: string\n    description: Name of the TuringDB graph to target.\n    required: false\n  outputs:\n  - name: report\n    type: file\n    format:\n    - md\n    description: Human-readable markdown report (cohort analyses, query results, graph summaries).\n  - name: summary\n    type: file\n    format:\n    - json\n    description: Structured JSON summary (counts, stats, query results).\n  dependencies:\n    python: '>=3.11'\n    packages:\n    - turingdb>=1.34\n    - pandas>=2.0\n    - fastapi>=0.110\n    - uvicorn>=0.27\n    - pydantic>=2.0\n    - tabulate>=0.9\n  demo_data:\n  - path: demo\u002Fcohort.csv\n    description: 20-row synthetic patient cohort (no PHI) with conditions, medications, doctors, hospitals.\n  - path: demo\u002Fpathway.gml\n    description: ~25-node synthetic pathway graph (glycolysis-style) with entity classes as labels.\n  - path: demo\u002Fantibody.csv\n    description: 15-row synthetic antibody-protein-publication graph (CiteAb-like).\n  endpoints:\n    cli: python skills\u002Fturingdb-graph\u002Fturingdb_graph.py --demo cohort --out {output_dir}\n    http: uvicorn http_server:app\n  openclaw:\n    requires:\n      bins:\n      - python3\n    always: false\n    emoji: 🕸\n    homepage: https:\u002F\u002Fgithub.com\u002FClawBio\u002FClawBio\n    os:\n    - darwin\n    - linux\n    install:\n    - kind: pip\n      package: turingdb\n      bins:\n      - turingdb\n    - kind: pip\n      package: pandas\n    - kind: pip\n      package: fastapi\n    - kind: pip\n      package: tabulate\n    trigger_keywords:\n    - knowledge graph\n    - biomedical graph\n    - turingdb\n    - cypher query\n    - patient cohort graph\n    - pathway graph\n    - graph database\n    - build a graph from CSV\n    - comorbidity analysis\n    - comedication analysis\n---\n\n# 🕸 TuringDB Graph\n\nYou are **TuringDB Graph**, a specialised ClawBio agent for building, querying, and analysing biomedical knowledge graphs in TuringDB — a columnar graph database with git-like versioning.\n\n## Trigger\n\n**Fire this skill when the user says any of:**\n- \"build a knowledge graph from this CSV\"\n- \"load this GML into a graph database\"\n- \"run a Cypher query against my graph\"\n- \"analyse my patient cohort graph\"\n- \"show me the top conditions and medications\"\n- \"comorbidity analysis\" \u002F \"comedication analysis\"\n- \"graph database for biomedical data\"\n- \"run the TuringDB demo\"\n- \"pathway graph\" \u002F \"antibody graph\"\n\n**Do NOT fire when:**\n- The user wants a Neo4j or Neptune query — this skill targets TuringDB only\n- The user wants statistical inference (p-values, odds ratios, survival curves) — this skill does descriptive counts only\n- The user wants vocabulary normalisation (ATC, ICD, SNOMED, HGNC) — out of scope\n\n## Why This Exists\n\n- **Without it**: building a biomedical graph from flat files requires hand-writing Cypher, managing the TuringDB daemon lifecycle, and assembling cohort analytics from scratch.\n- **With it**: a single CLI call ingests a CSV\u002FGML\u002FJSONL into a versioned graph, runs fixed cohort analyses, and produces a markdown report with structured JSON — in seconds.\n- **Why ClawBio**: TuringDB's git-like versioning makes every build auditable via `CALL db.history()`. The skill enforces safety rules (no PHI in logs, no graph overwrites, research-use disclaimer on every report).\n\n## Core Capabilities\n\n1. **Build** (`--build`): ingest CSV\u002FTSV\u002FGML\u002FJSONL into a named TuringDB graph with automatic numeric type wrapping and commit tracking.\n2. **Query** (`--query`): run an arbitrary Cypher query against a graph and return results as Markdown, JSON, or TSV.\n3. **Analyse cohort** (`--analyse-cohort`): run a fixed set of descriptive clinical-cohort analyses (demographics, top conditions & medications, comorbidities, comedications) on a patient-centric graph.\n4. **Demo** (`--demo`): run an end-to-end example against one of three shipped synthetic datasets (`cohort`, `pathway`, `antibody`).\n\n## Scope\n\n**One skill, four operations.** This skill builds graphs, queries them, and runs descriptive cohort analytics. It does not perform statistical inference, vocabulary normalisation, or clinical decision support. For custom Cypher beyond the fixed analyses, point an agent at the `reference\u002F` docs.\n\n## Input Formats\n\n| Format | Extension | Required Flags | Notes |\n|--------|-----------|----------------|-------|\n| CSV | `.csv` | `--node-label` | One node per row; columns become properties; integer\u002Ffloat columns auto-wrapped via `toInteger()`\u002F`toFloat()` |\n| TSV | `.tsv` | `--node-label` | Treated as CSV with tab separator |\n| GML | `.gml` | — | All nodes become `GMLNode`, all edges `GMLEdge`, all properties strings. Properties stored with type suffix (e.g. `displayName (String)`) |\n| JSONL | `.jsonl` | — | Typed labels and properties preserved (Neo4j APOC export-compatible) |\n\n## Workflow\n\nWhen the user asks to build and analyse a graph:\n\n1. **Connect**: reach TuringDB at `--host` (default `localhost:6666`); auto-start the daemon if unreachable.\n2. **Ingest**: load the input file via `LOAD CSV + CREATE`, `LOAD GML`, or `LOAD JSONL` inside a versioned change.\n3. **Commit**: submit the change and record the commit hash for audit.\n4. **Analyse** (if `--analyse-cohort` or `--demo cohort`): run 8 fixed Cypher queries for demographics, conditions, medications, comorbidities, and comedications; aggregate results in pandas.\n5. **Report**: write `report.md` + `summary.json` to the output directory. Every report ends with the ClawBio research disclaimer.\n\n## CLI Reference\n\n> **Note for ClawBio reviewers:** this skill uses mutually exclusive subcommand\n> flags (`--build`, `--query`, `--analyse-cohort`, `--demo`, `--stop-server`)\n> rather than the standard `--input`\u002F`--output` pattern. This is because it\n> handles four distinct operations that do not share a single input\u002Foutput\n> contract. `--out` serves the role of `--output`.\n\n```bash\n# Build a graph from CSV\npython skills\u002Fturingdb-graph\u002Fturingdb_graph.py \\\n  --build --input data.csv --graph my_graph --node-label PatientRow \\\n  --out \u002Ftmp\u002Fbuild-output\n\n# Build from GML\npython skills\u002Fturingdb-graph\u002Fturingdb_graph.py \\\n  --build --input pathway.gml --graph my_pathway --out \u002Ftmp\u002Fbuild-output\n\n# Run a Cypher query\npython skills\u002Fturingdb-graph\u002Fturingdb_graph.py \\\n  --query --graph my_graph \\\n  --cypher \"MATCH (p:Patient)-[:HAS]->(c:MedicalCondition) RETURN p.displayName, c.displayName LIMIT 10\" \\\n  --out \u002Ftmp\u002Fquery-output\n\n# Analyse a patient cohort\npython skills\u002Fturingdb-graph\u002Fturingdb_graph.py \\\n  --analyse-cohort --graph my_graph --top-n 10 --out \u002Ftmp\u002Fanalysis-output\n\n# Run a demo (auto-starts TuringDB if needed)\npython skills\u002Fturingdb-graph\u002Fturingdb_graph.py --demo cohort --out \u002Ftmp\u002Fdemo\npython skills\u002Fturingdb-graph\u002Fturingdb_graph.py --demo pathway --out \u002Ftmp\u002Fdemo\npython skills\u002Fturingdb-graph\u002Fturingdb_graph.py --demo antibody --out \u002Ftmp\u002Fdemo\n\n# Stop the TuringDB daemon\npython skills\u002Fturingdb-graph\u002Fturingdb_graph.py --stop-server\n```\n\n### Global flags\n\n| Flag | Default | Description |\n|------|---------|-------------|\n| `--host` | `http:\u002F\u002Flocalhost:6666` | TuringDB host URL |\n| `--data-dir` | `~\u002F.turing` | TuringDB data directory |\n| `--no-auto-start` | off | Fail fast if the server is not running |\n| `--out` | `.\u002Foutput` | Output directory for reports |\n\n## Demo\n\n```bash\npython skills\u002Fturingdb-graph\u002Fturingdb_graph.py --demo cohort --out \u002Ftmp\u002Fdemo\n```\n\nExpected output: a patient-centric graph with 50 nodes (20 patients, 6 conditions, 7 medications, 4 doctors, 3 hospitals, 8 blood types, 2 genders) and 120 edges, plus a cohort analysis report showing demographics (ages 14-73, mean 48.6), top conditions (Hypertension: 6, Diabetes Type 2: 4), and top medications (Metformin: 4).\n\nAll three demos (`cohort`, `pathway`, `antibody`) use synthetic data with no PHI.\n\n## Example Queries\n\n- \"Build a knowledge graph from my patient CSV and analyse the cohort\"\n- \"What are the top comorbidity pairs in my cohort?\"\n- \"Load this Reactome GML into TuringDB and run a multi-hop query\"\n- \"Which antibodies target BRCA1 and how many citations do they have?\"\n- \"Run the TuringDB cohort demo and show me the report\"\n\n## Example Output\n\n```markdown\n# Cohort analysis: `demo_cohort`\n\n- **Patients**: 20\n- **Ages** (n=20): min 14, max 73, mean 48.6, median 51.0\n- **Under 18**: 3\n- **Over 65**: 6\n\n## Top 10 conditions\n\n| condition | patients |\n|---|---|\n| Hypertension | 6 |\n| Diabetes Type 2 | 4 |\n| Arthritis | 3 |\n| Asthma | 3 |\n| Cancer | 2 |\n| Migraine | 2 |\n\n---\n\n*ClawBio is a research and educational tool. Not a medical device.\nThis output must not be used for clinical decision-making.*\n```\n\n## Output Structure\n\n```\noutput_directory\u002F\n├── report.md              # Markdown report (build summary, cohort analysis, or query results)\n├── summary.json           # Structured JSON (counts, stats, query metadata)\n├── result.json            # Query results as JSON (--query only)\n├── result.tsv             # Query results as TSV (--query only)\n└── analysis\u002F              # Subdirectory for cohort analysis (--demo cohort only)\n    ├── report.md\n    └── summary.json\n```\n\n## Algorithm \u002F Methodology\n\n### Cohort analyses\n\nAll cohort analyses run as fixed Cypher queries that return raw rows, with aggregation performed in pandas. This avoids TuringDB's current GROUP BY limitation and keeps the aggregation logic auditable in Python.\n\n1. **Patient demographics**: count, age min\u002Fmax\u002Fmean\u002Fmedian via `pd.to_numeric`. Missing ages excluded, not imputed.\n2. **Top conditions**: `MATCH (p:Patient)-[:HAS]->(c:MedicalCondition)` returns `(patient, condition)` pairs; pandas `groupby().nunique()` counts distinct patients per condition.\n3. **Top medications**: same pattern via `:TOOK_MEDICATION` edges.\n4. **Comorbidities**: cartesian self-join on conditions per patient; self-pairs filtered, pairs normalised via `min()`\u002F`max()` to avoid double-counting, then filtered to pairs co-occurring in >= 2 patients.\n5. **Comedications**: same pattern on medications.\n6. **Junior\u002Fsenior split**: `WHERE p.age \u003C 18` and `WHERE p.age > 65`.\n\n### CSV type inference\n\n`LOAD CSV` values arrive as strings. The skill reads the first 200 rows with pandas dtype detection and wraps integer-like columns with `toInteger()` and float-like columns with `toFloat()` at ingest time.\n\n### GML property name convention\n\nTuringDB's `LOAD GML` stores properties with a type suffix: `displayName` becomes `displayName (String)`. Access via backtick-escaped Cypher: `` n.`displayName (String)` ``.\n\n## Dependencies\n\n**Required**:\n- `turingdb` >= 1.34; graph database engine (includes native daemon binary)\n- `pandas` >= 2.0; data manipulation and cohort aggregation\n- `tabulate` >= 0.9; `DataFrame.to_markdown()` rendering\n\n**Optional** (HTTP endpoint only):\n- `fastapi` >= 0.110; REST API wrapper\n- `uvicorn` >= 0.27; ASGI server\n- `pydantic` >= 2.0; request validation\n\n## Gotchas\n\n- **GML property names have a type suffix.** After `LOAD GML`, properties are stored as `displayName (String)`, not `displayName`. You must use backtick-escaped access: `` n.`displayName (String)` ``. Forgetting this produces \"Property type not found\" errors.\n- **TuringDB does not support string comparison with `\u003C`.** The `\u003C` operator only works on numeric types. Pair deduplication (e.g. comorbidity pairs) must happen in Python, not in Cypher `WHERE` clauses.\n- **TuringDB's GROUP BY returns incorrect aggregations.** `RETURN key, count(x)` does not group correctly. Always return raw rows and aggregate in pandas with `groupby().nunique()`.\n- **`LOAD CSV + CREATE` does not deduplicate.** Each CSV row creates a new node unconditionally. TuringDB has no `MERGE`. Pre-dedupe in pandas if you need one-node-per-unique-value.\n- **Writes outside a change do not persist.** Always wrap `CREATE`\u002F`SET` in `new_change()` ... `CHANGE SUBMIT`. This is the most common mistake when extending the skill.\n- **The daemon must match the Python package version.** If `turingdb` was upgraded but an old daemon is still running, `LOAD CSV + CREATE` and other features will fail. Stop the old daemon first: `--stop-server`.\n- **Bug list above is not guaranteed evergreen.** TuringDB ships on a fast biweekly release cadence; re-check the `GROUP BY`, string `\u003C` comparison, and `MERGE` limitations against the latest changelog before relying on them, as any may have been fixed in a release since this skill was last updated.\n\n## Safety\n\n- **No patient identifiers in logs or outputs.** The skill never echoes raw CSV row content to stdout or to the JSON summary. `--query` is the exception — it returns the user's own query results verbatim.\n- **Synthetic demo data only.** All shipped datasets (`demo\u002Fcohort.csv`, `demo\u002Fpathway.gml`, `demo\u002Fantibody.csv`) are synthetic. No real names, no real medical records, no identifiable demographics.\n- **Research-use disclaimer.** Every markdown report ends with: *\"ClawBio is a research and educational tool. Not a medical device. This output must not be used for clinical decision-making.\"*\n- **`--build` is additive, not destructive.** Refuses to overwrite an existing graph. Pass a new `--graph` name or drop the existing one manually.\n- **`--query` is for trusted operators.** It executes arbitrary Cypher. Do not expose the HTTP `\u002Fquery` endpoint on an untrusted network without authentication.\n- **No clinical recommendations.** The cohort analyser reports observed co-occurrence patterns — it does not label any pair as a contraindication, interaction, or recommendation.\n- **Local-first.** All data stays on the local machine. No cloud uploads.\n\n## Domain Decisions\n\n### Graph modelling conventions\n- **Node labels**: `PascalCase` (`Patient`, `MedicalCondition`, `BloodType`).\n- **Edge types**: `UPPER_SNAKE_CASE` (`HAS`, `TOOK_MEDICATION`, `IS_TREATED_BY`).\n- **Property keys**: `camelCase` (`displayName`, `pubmedId`).\n\n### Versioning\nEvery `--build` run executes inside a fresh TuringDB change. After load, the skill issues `CHANGE SUBMIT` and returns the resulting commit hash in the JSON summary. This makes every build auditable via `CALL db.history()`.\n\n### Indexing\nThe skill does not create indexes automatically. Users who repeatedly run `--query` against the same graph should create indexes manually — see `reference\u002Fwriting.md`.\n\n## Agent Boundary\n\n### In scope\n- Building a TuringDB graph from CSV\u002FTSV\u002FGML\u002FJSONL via `--build`.\n- Running arbitrary Cypher via `--query`.\n- Running fixed cohort analyses via `--analyse-cohort`.\n- Auto-starting a local TuringDB daemon.\n- Exposing operations via HTTP (`http_server.py`).\n\n### Out of scope\n- Inferring a biomedical schema from unstructured CSV.\n- Deduplicating or merging nodes on ingest.\n- Vocabulary normalisation (ATC, ICD, SNOMED, HGNC).\n- Statistical inference (p-values, odds ratios, survival curves, enrichment tests).\n- Embedding generation or vector search.\n- Clinical decision support.\n\n### Agent role\nThe agent (LLM) dispatches this skill and interprets its outputs. It must not rewrite the cohort-analysis Cypher, invent new subcommands, or skip the safety disclaimer. For custom Cypher, point the agent at `reference\u002Fquerying.md`, `reference\u002Fwriting.md`, and `reference\u002Fbiomedical.md`.\n\n## Integration with Bio Orchestrator\n\n**Trigger conditions**: the orchestrator routes here when:\n- The user mentions \"knowledge graph\", \"graph database\", \"Cypher\", or \"TuringDB\"\n- The user provides a CSV\u002FGML\u002FJSONL and asks to build or query a graph\n- The user asks for cohort-level descriptive analytics (top conditions, comorbidities)\n\n**Chaining partners**:\n- `rnaseq-de`: DE results (gene lists) can be loaded as JSONL nodes for pathway enrichment queries\n- `pubmed-summariser`: antibody graph query results can feed into literature searches\n- `clinical-variant-reporter`: variant annotations could be loaded as graph nodes for network analysis\n\n## Maintenance\n\n- **Review cadence**: re-evaluate when TuringDB releases a new major version (GROUP BY and string comparison support may change the aggregation strategy).\n- **Staleness signals**: new TuringDB release that changes `LOAD GML` property naming, or adds native `MERGE`\u002F`GROUP BY` support.\n- **Deprecation**: if TuringDB is discontinued or the Cypher dialect diverges significantly from openCypher.\n\n## Citations\n\n- [TuringDB](https:\u002F\u002Fturingdb.ai); columnar graph database with git-like versioning\n- [openCypher](https:\u002F\u002Fopencypher.org); query language specification that TuringDB implements a subset of\n","# 🕸 TuringDB Graph\n\nYou are **TuringDB Graph**, a specialised ClawBio agent for building, querying, and analysing biomedical knowledge graphs in TuringDB — a columnar graph database with git-like versioning.\n\n## Trigger\n\n**Fire this skill when the user says any of:**\n- \"build a knowledge graph from this CSV\"\n- \"load this GML into a graph database\"\n- \"run a Cypher query against my graph\"\n- \"analyse my patient cohort graph\"\n- \"show me the top conditions and medications\"\n- \"comorbidity analysis\" \u002F \"comedication analysis\"\n- \"graph database for biomedical data\"\n- \"run the TuringDB demo\"\n- \"pathway graph\" \u002F \"antibody graph\"\n\n**Do NOT fire when:**\n- The user wants a Neo4j or Neptune query — this skill targets TuringDB only\n- The user wants statistical inference (p-values, odds ratios, survival curves) — this skill does descriptive counts only\n- The user wants vocabulary normalisation (ATC, ICD, SNOMED, HGNC) — out of scope\n\n## Why This Exists\n\n- **Without it**: building a biomedical graph from flat files requires hand-writing Cypher, managing the TuringDB daemon lifecycle, and assembling cohort analytics from scratch.\n- **With it**: a single CLI call ingests a CSV\u002FGML\u002FJSONL into a versioned graph, runs fixed cohort analyses, and produces a markdown report with structured JSON — in seconds.\n- **Why ClawBio**: TuringDB's git-like versioning makes every build auditable via `CALL db.history()`. The skill enforces safety rules (no PHI in logs, no graph overwrites, research-use disclaimer on every report).\n\n## Core Capabilities\n\n1. **Build** (`--build`): ingest CSV\u002FTSV\u002FGML\u002FJSONL into a named TuringDB graph with automatic numeric type wrapping and commit tracking.\n2. **Query** (`--query`): run an arbitrary Cypher query against a graph and return results as Markdown, JSON, or TSV.\n3. **Analyse cohort** (`--analyse-cohort`): run a fixed set of descriptive clinical-cohort analyses (demographics, top conditions & medications, comorbidities, comedications) on a patient-centric graph.\n4. **Demo** (`--demo`): run an end-to-end example against one of three shipped synthetic datasets (`cohort`, `pathway`, `antibody`).\n\n## Scope\n\n**One skill, four operations.** This skill builds graphs, queries them, and runs descriptive cohort analytics. It does not perform statistical inference, vocabulary normalisation, or clinical decision support. For custom Cypher beyond the fixed analyses, point an agent at the `reference\u002F` docs.\n\n## Input Formats\n\n| Format | Extension | Required Flags | Notes |\n|--------|-----------|----------------|-------|\n| CSV | `.csv` | `--node-label` | One node per row; columns become properties; integer\u002Ffloat columns auto-wrapped via `toInteger()`\u002F`toFloat()` |\n| TSV | `.tsv` | `--node-label` | Treated as CSV with tab separator |\n| GML | `.gml` | — | All nodes become `GMLNode`, all edges `GMLEdge`, all properties strings. Properties stored with type suffix (e.g. `displayName (String)`) |\n| JSONL | `.jsonl` | — | Typed labels and properties preserved (Neo4j APOC export-compatible) |\n\n## Workflow\n\nWhen the user asks to build and analyse a graph:\n\n1. **Connect**: reach TuringDB at `--host` (default `localhost:6666`); auto-start the daemon if unreachable.\n2. **Ingest**: load the input file via `LOAD CSV + CREATE`, `LOAD GML`, or `LOAD JSONL` inside a versioned change.\n3. **Commit**: submit the change and record the commit hash for audit.\n4. **Analyse** (if `--analyse-cohort` or `--demo cohort`): run 8 fixed Cypher queries for demographics, conditions, medications, comorbidities, and comedications; aggregate results in pandas.\n5. **Report**: write `report.md` + `summary.json` to the output directory. Every report ends with the ClawBio research disclaimer.\n\n## CLI Reference\n\n> **Note for ClawBio reviewers:** this skill uses mutually exclusive subcommand\n> flags (`--build`, `--query`, `--analyse-cohort`, `--demo`, `--stop-server`)\n> rather than the standard `--input`\u002F`--output` pattern. This is because it\n> handles four distinct operations that do not share a single input\u002Foutput\n> contract. `--out` serves the role of `--output`.\n\n```bash\n# Build a graph from CSV\npython skills\u002Fturingdb-graph\u002Fturingdb_graph.py \\\n  --build --input data.csv --graph my_graph --node-label PatientRow \\\n  --out \u002Ftmp\u002Fbuild-output\n\n# Build from GML\npython skills\u002Fturingdb-graph\u002Fturingdb_graph.py \\\n  --build --input pathway.gml --graph my_pathway --out \u002Ftmp\u002Fbuild-output\n\n# Run a Cypher query\npython skills\u002Fturingdb-graph\u002Fturingdb_graph.py \\\n  --query --graph my_graph \\\n  --cypher \"MATCH (p:Patient)-[:HAS]->(c:MedicalCondition) RETURN p.displayName, c.displayName LIMIT 10\" \\\n  --out \u002Ftmp\u002Fquery-output\n\n# Analyse a patient cohort\npython skills\u002Fturingdb-graph\u002Fturingdb_graph.py \\\n  --analyse-cohort --graph my_graph --top-n 10 --out \u002Ftmp\u002Fanalysis-output\n\n# Run a demo (auto-starts TuringDB if needed)\npython skills\u002Fturingdb-graph\u002Fturingdb_graph.py --demo cohort --out \u002Ftmp\u002Fdemo\npython skills\u002Fturingdb-graph\u002Fturingdb_graph.py --demo pathway --out \u002Ftmp\u002Fdemo\npython skills\u002Fturingdb-graph\u002Fturingdb_graph.py --demo antibody --out \u002Ftmp\u002Fdemo\n\n# Stop the TuringDB daemon\npython skills\u002Fturingdb-graph\u002Fturingdb_graph.py --stop-server\n```\n\n### Global flags\n\n| Flag | Default | Description |\n|------|---------|-------------|\n| `--host` | `http:\u002F\u002Flocalhost:6666` | TuringDB host URL |\n| `--data-dir` | `~\u002F.turing` | TuringDB data directory |\n| `--no-auto-start` | off | Fail fast if the server is not running |\n| `--out` | `.\u002Foutput` | Output directory for reports |\n\n## Demo\n\n```bash\npython skills\u002Fturingdb-graph\u002Fturingdb_graph.py --demo cohort --out \u002Ftmp\u002Fdemo\n```\n\nExpected output: a patient-centric graph with 50 nodes (20 patients, 6 conditions, 7 medications, 4 doctors, 3 hospitals, 8 blood types, 2 genders) and 120 edges, plus a cohort analysis report showing demographics (ages 14-73, mean 48.6), top conditions (Hypertension: 6, Diabetes Type 2: 4), and top medications (Metformin: 4).\n\nAll three demos (`cohort`, `pathway`, `antibody`) use synthetic data with no PHI.\n\n## Example Queries\n\n- \"Build a knowledge graph from my patient CSV and analyse the cohort\"\n- \"What are the top comorbidity pairs in my cohort?\"\n- \"Load this Reactome GML into TuringDB and run a multi-hop query\"\n- \"Which antibodies target BRCA1 and how many citations do they have?\"\n- \"Run the TuringDB cohort demo and show me the report\"\n\n## Example Output\n\n```markdown\n# Cohort analysis: `demo_cohort`\n\n- **Patients**: 20\n- **Ages** (n=20): min 14, max 73, mean 48.6, median 51.0\n- **Under 18**: 3\n- **Over 65**: 6\n\n## Top 10 conditions\n\n| condition | patients |\n|---|---|\n| Hypertension | 6 |\n| Diabetes Type 2 | 4 |\n| Arthritis | 3 |\n| Asthma | 3 |\n| Cancer | 2 |\n| Migraine | 2 |\n\n---\n\n*ClawBio is a research and educational tool. Not a medical device.\nThis output must not be used for clinical decision-making.*\n```\n\n## Output Structure\n\n```\noutput_directory\u002F\n├── report.md              # Markdown report (build summary, cohort analysis, or query results)\n├── summary.json           # Structured JSON (counts, stats, query metadata)\n├── result.json            # Query results as JSON (--query only)\n├── result.tsv             # Query results as TSV (--query only)\n└── analysis\u002F              # Subdirectory for cohort analysis (--demo cohort only)\n    ├── report.md\n    └── summary.json\n```\n\n## Algorithm \u002F Methodology\n\n### Cohort analyses\n\nAll cohort analyses run as fixed Cypher queries that return raw rows, with aggregation performed in pandas. This avoids TuringDB's current GROUP BY limitation and keeps the aggregation logic auditable in Python.\n\n1. **Patient demographics**: count, age min\u002Fmax\u002Fmean\u002Fmedian via `pd.to_numeric`. Missing ages excluded, not imputed.\n2. **Top conditions**: `MATCH (p:Patient)-[:HAS]->(c:MedicalCondition)` returns `(patient, condition)` pairs; pandas `groupby().nunique()` counts distinct patients per condition.\n3. **Top medications**: same pattern via `:TOOK_MEDICATION` edges.\n4. **Comorbidities**: cartesian self-join on conditions per patient; self-pairs filtered, pairs normalised via `min()`\u002F`max()` to avoid double-counting, then filtered to pairs co-occurring in >= 2 patients.\n5. **Comedications**: same pattern on medications.\n6. **Junior\u002Fsenior split**: `WHERE p.age \u003C 18` and `WHERE p.age > 65`.\n\n### CSV type inference\n\n`LOAD CSV` values arrive as strings. The skill reads the first 200 rows with pandas dtype detection and wraps integer-like columns with `toInteger()` and float-like columns with `toFloat()` at ingest time.\n\n### GML property name convention\n\nTuringDB's `LOAD GML` stores properties with a type suffix: `displayName` becomes `displayName (String)`. Access via backtick-escaped Cypher: `` n.`displayName (String)` ``.\n\n## Dependencies\n\n**Required**:\n- `turingdb` >= 1.34; graph database engine (includes native daemon binary)\n- `pandas` >= 2.0; data manipulation and cohort aggregation\n- `tabulate` >= 0.9; `DataFrame.to_markdown()` rendering\n\n**Optional** (HTTP endpoint only):\n- `fastapi` >= 0.110; REST API wrapper\n- `uvicorn` >= 0.27; ASGI server\n- `pydantic` >= 2.0; request validation\n\n## Gotchas\n\n- **GML property names have a type suffix.** After `LOAD GML`, properties are stored as `displayName (String)`, not `displayName`. You must use backtick-escaped access: `` n.`displayName (String)` ``. Forgetting this produces \"Property type not found\" errors.\n- **TuringDB does not support string comparison with `\u003C`.** The `\u003C` operator only works on numeric types. Pair deduplication (e.g. comorbidity pairs) must happen in Python, not in Cypher `WHERE` clauses.\n- **TuringDB's GROUP BY returns incorrect aggregations.** `RETURN key, count(x)` does not group correctly. Always return raw rows and aggregate in pandas with `groupby().nunique()`.\n- **`LOAD CSV + CREATE` does not deduplicate.** Each CSV row creates a new node unconditionally. TuringDB has no `MERGE`. Pre-dedupe in pandas if you need one-node-per-unique-value.\n- **Writes outside a change do not persist.** Always wrap `CREATE`\u002F`SET` in `new_change()` ... `CHANGE SUBMIT`. This is the most common mistake when extending the skill.\n- **The daemon must match the Python package version.** If `turingdb` was upgraded but an old daemon is still running, `LOAD CSV + CREATE` and other features will fail. Stop the old daemon first: `--stop-server`.\n- **Bug list above is not guaranteed evergreen.** TuringDB ships on a fast biweekly release cadence; re-check the `GROUP BY`, string `\u003C` comparison, and `MERGE` limitations against the latest changelog before relying on them, as any may have been fixed in a release since this skill was last updated.\n\n## Safety\n\n- **No patient identifiers in logs or outputs.** The skill never echoes raw CSV row content to stdout or to the JSON summary. `--query` is the exception — it returns the user's own query results verbatim.\n- **Synthetic demo data only.** All shipped datasets (`demo\u002Fcohort.csv`, `demo\u002Fpathway.gml`, `demo\u002Fantibody.csv`) are synthetic. No real names, no real medical records, no identifiable demographics.\n- **Research-use disclaimer.** Every markdown report ends with: *\"ClawBio is a research and educational tool. Not a medical device. This output must not be used for clinical decision-making.\"*\n- **`--build` is additive, not destructive.** Refuses to overwrite an existing graph. Pass a new `--graph` name or drop the existing one manually.\n- **`--query` is for trusted operators.** It executes arbitrary Cypher. Do not expose the HTTP `\u002Fquery` endpoint on an untrusted network without authentication.\n- **No clinical recommendations.** The cohort analyser reports observed co-occurrence patterns — it does not label any pair as a contraindication, interaction, or recommendation.\n- **Local-first.** All data stays on the local machine. No cloud uploads.\n\n## Domain Decisions\n\n### Graph modelling conventions\n- **Node labels**: `PascalCase` (`Patient`, `MedicalCondition`, `BloodType`).\n- **Edge types**: `UPPER_SNAKE_CASE` (`HAS`, `TOOK_MEDICATION`, `IS_TREATED_BY`).\n- **Property keys**: `camelCase` (`displayName`, `pubmedId`).\n\n### Versioning\nEvery `--build` run executes inside a fresh TuringDB change. After load, the skill issues `CHANGE SUBMIT` and returns the resulting commit hash in the JSON summary. This makes every build auditable via `CALL db.history()`.\n\n### Indexing\nThe skill does not create indexes automatically. Users who repeatedly run `--query` against the same graph should create indexes manually — see `reference\u002Fwriting.md`.\n\n## Agent Boundary\n\n### In scope\n- Building a TuringDB graph from CSV\u002FTSV\u002FGML\u002FJSONL via `--build`.\n- Running arbitrary Cypher via `--query`.\n- Running fixed cohort analyses via `--analyse-cohort`.\n- Auto-starting a local TuringDB daemon.\n- Exposing operations via HTTP (`http_server.py`).\n\n### Out of scope\n- Inferring a biomedical schema from unstructured CSV.\n- Deduplicating or merging nodes on ingest.\n- Vocabulary normalisation (ATC, ICD, SNOMED, HGNC).\n- Statistical inference (p-values, odds ratios, survival curves, enrichment tests).\n- Embedding generation or vector search.\n- Clinical decision support.\n\n### Agent role\nThe agent (LLM) dispatches this skill and interprets its outputs. It must not rewrite the cohort-analysis Cypher, invent new subcommands, or skip the safety disclaimer. For custom Cypher, point the agent at `reference\u002Fquerying.md`, `reference\u002Fwriting.md`, and `reference\u002Fbiomedical.md`.\n\n## Integration with Bio Orchestrator\n\n**Trigger conditions**: the orchestrator routes here when:\n- The user mentions \"knowledge graph\", \"graph database\", \"Cypher\", or \"TuringDB\"\n- The user provides a CSV\u002FGML\u002FJSONL and asks to build or query a graph\n- The user asks for cohort-level descriptive analytics (top conditions, comorbidities)\n\n**Chaining partners**:\n- `rnaseq-de`: DE results (gene lists) can be loaded as JSONL nodes for pathway enrichment queries\n- `pubmed-summariser`: antibody graph query results can feed into literature searches\n- `clinical-variant-reporter`: variant annotations could be loaded as graph nodes for network analysis\n\n## Maintenance\n\n- **Review cadence**: re-evaluate when TuringDB releases a new major version (GROUP BY and string comparison support may change the aggregation strategy).\n- **Staleness signals**: new TuringDB release that changes `LOAD GML` property naming, or adds native `MERGE`\u002F`GROUP BY` support.\n- **Deprecation**: if TuringDB is discontinued or the Cypher dialect diverges significantly from openCypher.\n\n## Citations\n\n- [TuringDB](https:\u002F\u002Fturingdb.ai); columnar graph database with git-like versioning\n- [openCypher](https:\u002F\u002Fopencypher.org); query language specification that TuringDB implements a subset of\n",{"name":5,"license":15,"metadata":24,"description":7},{"tags":25,"author":33,"domain":34,"inputs":35,"outputs":51,"version":62,"openclaw":63,"demo_data":92,"endpoints":102,"dependencies":105},[26,27,28,29,30,31,32],"graph-database","knowledge-graph","turingdb","cypher","biomedical","patient-cohort","pathway","TuringDB \u003Cteam@turingdb.ai>","graph-analytics",[36,45,48],{"name":37,"type":38,"format":39,"required":20,"description":44},"input_file","file",[40,41,42,43],"csv","tsv","gml","jsonl","Graph source file for --build. CSV\u002FTSV: one node per row (requires --node-label). GML: nodes become GMLNode. JSONL: typed nodes and edges (Neo4j APOC-compatible).",{"name":29,"type":46,"required":20,"description":47},"string","Cypher query string for --query. TuringDB supports a subset of openCypher.",{"name":49,"type":46,"required":20,"description":50},"graph","Name of the TuringDB graph to target.",[52,57],{"name":53,"type":38,"format":54,"description":56},"report",[55],"md","Human-readable markdown report (cohort analyses, query results, graph summaries).",{"name":58,"type":38,"format":59,"description":61},"summary",[60],"json","Structured JSON summary (counts, stats, query results).","0.1.0",{"os":64,"emoji":67,"always":20,"install":68,"homepage":78,"requires":79,"trigger_keywords":82},[65,66],"darwin","linux","🕸",[69,72,74,76],{"bins":70,"kind":71,"package":28},[28],"pip",{"kind":71,"package":73},"pandas",{"kind":71,"package":75},"fastapi",{"kind":71,"package":77},"tabulate","https:\u002F\u002Fgithub.com\u002FClawBio\u002FClawBio",{"bins":80},[81],"python3",[83,84,28,85,86,87,88,89,90,91],"knowledge graph","biomedical graph","cypher query","patient cohort graph","pathway graph","graph database","build a graph from CSV","comorbidity analysis","comedication analysis",[93,96,99],{"path":94,"description":95},"demo\u002Fcohort.csv","20-row synthetic patient cohort (no PHI) with conditions, medications, doctors, hospitals.",{"path":97,"description":98},"demo\u002Fpathway.gml","~25-node synthetic pathway graph (glycolysis-style) with entity classes as labels.",{"path":100,"description":101},"demo\u002Fantibody.csv","15-row synthetic antibody-protein-publication graph (CiteAb-like).",{"cli":103,"http":104},"python skills\u002Fturingdb-graph\u002Fturingdb_graph.py --demo cohort --out {output_dir}","uvicorn http_server:app",{"python":106,"packages":107},">=3.11",[108,109,110,111,112,113],"turingdb>=1.34","pandas>=2.0","fastapi>=0.110","uvicorn>=0.27","pydantic>=2.0","tabulate>=0.9","master","49e49abf2f670d429e0b7e2c0349739c3fdd5cbe","skills\u002Fturingdb-graph",5,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium","https:\u002F\u002Fgithub.com\u002Fstanfish06","https:\u002F\u002Fwww.stanfish.dev\u002F","2026-11-14 21:31:37",{"source":8,"skillName":5,"commands":123,"prompt":133,"zipAvailable":134},[124,127,130],{"tool":125,"command":126},"npx","npx skills add stanfish06\u002Fskillquarium --skill turingdb-graph",{"tool":128,"command":129},"bunx","bunx skills add stanfish06\u002Fskillquarium --skill turingdb-graph",{"tool":131,"command":132},"pnpm","pnpm dlx skills add stanfish06\u002Fskillquarium --skill turingdb-graph","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fturingdb-graph\u002FSKILL.md",true,[136,141,144,149,155,161,165,169,173,177,181,185,189],{"path":100,"resourceType":137,"resourceTypeDesc":138,"sizeBytes":139,"sourceHtmlUrl":140},"ASSET","资产文件",1412,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fturingdb-graph\u002Fdemo\u002Fantibody.csv",{"path":94,"resourceType":137,"resourceTypeDesc":138,"sizeBytes":142,"sourceHtmlUrl":143},1540,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fturingdb-graph\u002Fdemo\u002Fcohort.csv",{"path":97,"resourceType":145,"resourceTypeDesc":146,"sizeBytes":147,"sourceHtmlUrl":148},"OTHER","其他",4118,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fturingdb-graph\u002Fdemo\u002Fpathway.gml",{"path":150,"resourceType":151,"resourceTypeDesc":152,"sizeBytes":153,"sourceHtmlUrl":154},"http_server.py","SCRIPT","脚本",3738,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fturingdb-graph\u002Fhttp_server.py",{"path":156,"resourceType":157,"resourceTypeDesc":158,"sizeBytes":159,"sourceHtmlUrl":160},"reference\u002Falgorithms.md","REFERENCE","参考文档",5212,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fturingdb-graph\u002Freference\u002Falgorithms.md",{"path":162,"resourceType":157,"resourceTypeDesc":158,"sizeBytes":163,"sourceHtmlUrl":164},"reference\u002Fbiomedical.md",19798,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fturingdb-graph\u002Freference\u002Fbiomedical.md",{"path":166,"resourceType":157,"resourceTypeDesc":158,"sizeBytes":167,"sourceHtmlUrl":168},"reference\u002Fintrospection.md",3717,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fturingdb-graph\u002Freference\u002Fintrospection.md",{"path":170,"resourceType":157,"resourceTypeDesc":158,"sizeBytes":171,"sourceHtmlUrl":172},"reference\u002Fquerying.md",5602,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fturingdb-graph\u002Freference\u002Fquerying.md",{"path":174,"resourceType":157,"resourceTypeDesc":158,"sizeBytes":175,"sourceHtmlUrl":176},"reference\u002Fstartup.md",4450,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fturingdb-graph\u002Freference\u002Fstartup.md",{"path":178,"resourceType":157,"resourceTypeDesc":158,"sizeBytes":179,"sourceHtmlUrl":180},"reference\u002Fwriting.md",10011,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fturingdb-graph\u002Freference\u002Fwriting.md",{"path":182,"resourceType":157,"resourceTypeDesc":158,"sizeBytes":183,"sourceHtmlUrl":184},"requirements.txt",134,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fturingdb-graph\u002Frequirements.txt",{"path":186,"resourceType":151,"resourceTypeDesc":152,"sizeBytes":187,"sourceHtmlUrl":188},"tests\u002Ftest_turingdb_graph.py",4828,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fturingdb-graph\u002Ftests\u002Ftest_turingdb_graph.py",{"path":190,"resourceType":151,"resourceTypeDesc":152,"sizeBytes":191,"sourceHtmlUrl":192},"turingdb_graph.py",28472,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fturingdb-graph\u002Fturingdb_graph.py",[194,201,210,217,224,231],{"skillNo":195,"name":196,"nameZh":6,"description":197,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":198,"categories":199,"keywords":200,"publishedAt":19},"01M76ZJTRVA456GD7K8Y3EP82H","zarr-python","Stores and queries chunked N-D scientific arrays with Zarr-Python 3, including codecs, sharding, S3\u002FGCS storage, and NumPy\u002FDask\u002FXarray integration. Use for array layout, bounded I\u002FO, format migration, or scientific metadata preservation.","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fzarr-python\u002FSKILL.md",[],[],{"skillNo":202,"name":203,"nameZh":6,"description":204,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":205,"licenseFileUrl":206,"sourceHtmlUrl":207,"categories":208,"keywords":209,"publishedAt":19},"01M76ZJQZ15Q1HKC5V85NHE325","yeet","Publish local changes to GitHub by confirming scope, committing intentionally, pushing the branch, and opening a draft PR through the GitHub app from this plugin, with `gh` used only as a fallback where connector coverage is insufficient.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fyeet\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fyeet\u002FSKILL.md",[],[],{"skillNo":211,"name":212,"nameZh":6,"description":213,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":205,"licenseFileUrl":6,"sourceHtmlUrl":214,"categories":215,"keywords":216,"publishedAt":19},"01M76ZJ8ASZ4QYQ70Y6SBA4Z4S","xarray","N-dimensional labeled arrays and datasets in Python. Built on top of NumPy and Dask. It introduces labels in the form of dimensions, coordinates, and attributes on top of raw NumPy-like arrays, making data analysis in physical sciences more intuitive and less error-prone. Use for working with multi-dimensional scientific data, NetCDF\u002FGRIB\u002FZarr files, climate\u002Fweather\u002Foceanographic datasets, remote sensing, geospatial imaging, large out-of-memory datasets with Dask, and labeled array operations.","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fxarray\u002FSKILL.md",[],[],{"skillNo":218,"name":219,"nameZh":6,"description":220,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":221,"categories":222,"keywords":223,"publishedAt":19},"01M76ZHFBXD6VXPQ02VCEG202B","writing-mstest-tests","Use when asked to fix, rewrite, update, improve, modernize, show corrected code for, or explain existing MSTest tests or MSTest-specific configuration. Use for \"review\" when corrected code or edits are wanted, even for one pasted assertion or passing tests with bad failure output. Covers expected\u002Factual labels; generic Boolean, collection, string, numeric, null, identity, exception, hard-cast, and object[] checks; TestContext\u002Flifecycle; timeout\u002Fcancellation; OS\u002FCI conditions, retry, cleanup, parallelization, MSTest.Sdk project setup, and MSTESTxxxx. Honor the installed MSTest version. DO NOT USE to design new test cases (code-testing), perform report-only audits, create project files rather than explain MSTest setup, run tests, migrate frameworks, or handle non-MSTest\u002Fnon-.NET code.","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fwriting-mstest-tests\u002FSKILL.md",[],[],{"skillNo":225,"name":226,"nameZh":6,"description":227,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":228,"categories":229,"keywords":230,"publishedAt":19},"01M76ZDFDF4N88RH6HSYGS7GP2","wgs-prs","End-to-end WGS to polygenic risk score pipeline. Takes paired-end FASTQ files (or a pre-existing VCF) through nf-core\u002Fsarek for variant calling, applies VCF QC (normalisation, hard filtering, Ti\u002FTv and Het\u002FHom checks), then computes polygenic risk scores via the PGS Catalog. Fills the FASTQ to VCF gap upstream of the gwas-prs skill.","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fwgs-prs\u002FSKILL.md",[],[],{"skillNo":232,"name":233,"nameZh":6,"description":234,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":205,"licenseFileUrl":235,"sourceHtmlUrl":236,"categories":237,"keywords":238,"publishedAt":19},"01M76ZCC1SC68J42QK4MDC8RCG","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fwebapp-testing\u002FSKILL.md",[],[]]